Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc fixes from Benjamin Herrenschmidt:
 "This is mostly bug fixes (some of them regressions, some of them I
  deemed worth merging now) along with some patches from Li Zhong
  hooking up the new context tracking stuff (for the new full NO_HZ)"

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (25 commits)
  powerpc: Set show_unhandled_signals to 1 by default
  powerpc/perf: Fix setting of "to" addresses for BHRB
  powerpc/pmu: Fix order of interpreting BHRB target entries
  powerpc/perf: Move BHRB code into CONFIG_PPC64 region
  powerpc: select HAVE_CONTEXT_TRACKING for pSeries
  powerpc: Use the new schedule_user API on userspace preemption
  powerpc: Exit user context on notify resume
  powerpc: Exception hooks for context tracking subsystem
  powerpc: Syscall hooks for context tracking subsystem
  powerpc/booke64: Fix kernel hangs at kernel_dbg_exc
  powerpc: Fix irq_set_affinity() return values
  powerpc: Provide __bswapdi2
  powerpc/powernv: Fix starting of secondary CPUs on OPALv2 and v3
  powerpc/powernv: Detect OPAL v3 API version
  powerpc: Fix MAX_STACK_TRACE_ENTRIES too low warning again
  powerpc: Make CONFIG_RTAS_PROC depend on CONFIG_PROC_FS
  powerpc: Bring all threads online prior to migration/hibernation
  powerpc/rtas_flash: Fix validate_flash buffer overflow issue
  powerpc/kexec: Fix kexec when using VMX optimised memcpy
  powerpc: Fix build errors STRICT_MM_TYPECHECKS
  ...

11 files changed, 150 insertions, 10 deletions

diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index a881232a3cc..b62aab3e22e 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -128,7 +128,7 @@ config PPC_RTAS_DAEMON
 
 config RTAS_PROC
 	bool "Proc interface to RTAS"
-	depends on PPC_RTAS
+	depends on PPC_RTAS && PROC_FS
 	default y
 
 config RTAS_FLASH
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index ade4463226c..628c564cead 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
+#include <linux/slab.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
 
@@ -28,6 +29,8 @@ struct opal {
 static struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
 extern u64 opal_mc_secondary_handler[];
+static unsigned int *opal_irqs;
+static unsigned int opal_irq_count;
 
 int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
@@ -53,7 +56,11 @@ int __init early_init_dt_scan_opal(unsigned long node,
 		 opal.entry, entryp, entrysz);
 
 	powerpc_firmware_features |= FW_FEATURE_OPAL;
-	if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
+	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
+		powerpc_firmware_features |= FW_FEATURE_OPALv2;
+		powerpc_firmware_features |= FW_FEATURE_OPALv3;
+		printk("OPAL V3 detected !\n");
+	} else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
 		powerpc_firmware_features |= FW_FEATURE_OPALv2;
 		printk("OPAL V2 detected !\n");
 	} else {
@@ -144,6 +151,13 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 				rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
 		len = total_len;
 		rc = opal_console_write(vtermno, &len, data);
+
+		/* Closed or other error drop */
+		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
+		    rc != OPAL_BUSY_EVENT) {
+			written = total_len;
+			break;
+		}
 		if (rc == OPAL_SUCCESS) {
 			total_len -= len;
 			data += len;
@@ -316,6 +330,8 @@ static int __init opal_init(void)
 	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
 	pr_debug("opal: Found %d interrupts reserved for OPAL\n",
 		 irqs ? (irqlen / 4) : 0);
+	opal_irq_count = irqlen / 4;
+	opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
 	for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) {
 		unsigned int hwirq = be32_to_cpup(irqs);
 		unsigned int irq = irq_create_mapping(NULL, hwirq);
@@ -327,7 +343,19 @@ static int __init opal_init(void)
 		if (rc)
 			pr_warning("opal: Error %d requesting irq %d"
 				   " (0x%x)\n", rc, irq, hwirq);
+		opal_irqs[i] = irq;
 	}
 	return 0;
 }
 subsys_initcall(opal_init);
+
+void opal_shutdown(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < opal_irq_count; i++) {
+		if (opal_irqs[i])
+			free_irq(opal_irqs[i], 0);
+		opal_irqs[i] = 0;
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 1da578b7c1b..3937aaae5bc 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1048,6 +1048,12 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
 	return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
 }
 
+static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
+{
+	opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
+		       OPAL_ASSERT_RESET);
+}
+
 void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 {
 	struct pci_controller *hose;
@@ -1178,6 +1184,9 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 
+	/* Setup shutdown function for kexec */
+	phb->shutdown = pnv_pci_ioda_shutdown;
+
 	/* Setup MSI support */
 	pnv_pci_init_ioda_msis(phb);
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 55dfca844dd..163bd7422f1 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -450,6 +450,18 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
+void pnv_pci_shutdown(void)
+{
+	struct pci_controller *hose;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		struct pnv_phb *phb = hose->private_data;
+
+		if (phb && phb->shutdown)
+			phb->shutdown(phb);
+	}
+}
+
 /* Fixup wrong class code in p7ioc and p8 root complex */
 static void pnv_p7ioc_rc_quirk(struct pci_dev *dev)
 {
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 48dc4bb856a..25d76c4df50 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -86,6 +86,7 @@ struct pnv_phb {
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
+	void (*shutdown)(struct pnv_phb *phb);
 
 	union {
 		struct {
@@ -158,4 +159,5 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 					u64 *startp, u64 *endp);
+
 #endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 8a9df7f9667..a1c6f83fc39 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -9,8 +9,10 @@ static inline void pnv_smp_init(void) { }
 
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
+extern void pnv_pci_shutdown(void);
 #else
 static inline void pnv_pci_init(void) { }
+static inline void pnv_pci_shutdown(void) { }
 #endif
 
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index db1ad1c8f68..d4459bfc92f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -78,7 +78,9 @@ static void pnv_show_cpuinfo(struct seq_file *m)
 	if (root)
 		model = of_get_property(root, "model", NULL);
 	seq_printf(m, "machine\t\t: PowerNV %s\n", model);
-	if (firmware_has_feature(FW_FEATURE_OPALv2))
+	if (firmware_has_feature(FW_FEATURE_OPALv3))
+		seq_printf(m, "firmware\t: OPAL v3\n");
+	else if (firmware_has_feature(FW_FEATURE_OPALv2))
 		seq_printf(m, "firmware\t: OPAL v2\n");
 	else if (firmware_has_feature(FW_FEATURE_OPAL))
 		seq_printf(m, "firmware\t: OPAL v1\n");
@@ -126,6 +128,17 @@ static void pnv_progress(char *s, unsigned short hex)
 {
 }
 
+static void pnv_shutdown(void)
+{
+	/* Let the PCI code clear up IODA tables */
+	pnv_pci_shutdown();
+
+	/* And unregister all OPAL interrupts so they don't fire
+	 * up while we kexec
+	 */
+	opal_shutdown();
+}
+
 #ifdef CONFIG_KEXEC
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
@@ -187,6 +200,7 @@ define_machine(powernv) {
 	.init_IRQ		= pnv_init_IRQ,
 	.show_cpuinfo		= pnv_show_cpuinfo,
 	.progress		= pnv_progress,
+	.machine_shutdown	= pnv_shutdown,
 	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
 #ifdef CONFIG_KEXEC
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 6a3ecca5b72..88c9459c3e0 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -71,18 +71,68 @@ int pnv_smp_kick_cpu(int nr)
 
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
-	/* On OPAL v2 the CPU are still spinning inside OPAL itself,
-	 * get them back now
+	/*
+	 * If we already started or OPALv2 is not supported, we just
+	 * kick the CPU via the PACA
 	 */
-	if (!paca[nr].cpu_start && firmware_has_feature(FW_FEATURE_OPALv2)) {
-		pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu);
-		rc = opal_start_cpu(pcpu, start_here);
+	if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2))
+		goto kick;
+
+	/*
+	 * At this point, the CPU can either be spinning on the way in
+	 * from kexec or be inside OPAL waiting to be started for the
+	 * first time. OPAL v3 allows us to query OPAL to know if it
+	 * has the CPUs, so we do that
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPALv3)) {
+		uint8_t status;
+
+		rc = opal_query_cpu_status(pcpu, &status);
 		if (rc != OPAL_SUCCESS) {
-			pr_warn("OPAL Error %ld starting CPU %d\n",
+			pr_warn("OPAL Error %ld querying CPU %d state\n",
 				rc, nr);
 			return -ENODEV;
 		}
+
+		/*
+		 * Already started, just kick it, probably coming from
+		 * kexec and spinning
+		 */
+		if (status == OPAL_THREAD_STARTED)
+			goto kick;
+
+		/*
+		 * Available/inactive, let's kick it
+		 */
+		if (status == OPAL_THREAD_INACTIVE) {
+			pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n",
+				 nr, pcpu);
+			rc = opal_start_cpu(pcpu, start_here);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("OPAL Error %ld starting CPU %d\n",
+					rc, nr);
+				return -ENODEV;
+			}
+		} else {
+			/*
+			 * An unavailable CPU (or any other unknown status)
+			 * shouldn't be started. It should also
+			 * not be in the possible map but currently it can
+			 * happen
+			 */
+			pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable"
+				 " (status %d)...\n", nr, pcpu, status);
+			return -ENODEV;
+		}
+	} else {
+		/*
+		 * On OPAL v2, we just kick it and hope for the best,
+		 * we must not test the error from opal_start_cpu() or
+		 * we would fail to get CPUs from kexec.
+		 */
+		opal_start_cpu(pcpu, start_here);
 	}
+ kick:
 	return smp_generic_kick_cpu(nr);
 }
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 9a0941bc4d3..023b288f895 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -18,6 +18,7 @@ config PPC_PSERIES
 	select PPC_PCI_CHOICE if EXPERT
 	select ZLIB_DEFLATE
 	select PPC_DOORBELL
+	select HAVE_CONTEXT_TRACKING
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 47226e04126..5f997e79d57 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -16,6 +16,7 @@
   * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
   */
 
+#include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/suspend.h>
 #include <linux/stat.h>
@@ -126,11 +127,15 @@ static ssize_t store_hibernate(struct device *dev,
 			       struct device_attribute *attr,
 			       const char *buf, size_t count)
 {
+	cpumask_var_t offline_mask;
 	int rc;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
+		return -ENOMEM;
+
 	stream_id = simple_strtoul(buf, NULL, 16);
 
 	do {
@@ -140,15 +145,32 @@ static ssize_t store_hibernate(struct device *dev,
 	} while (rc == -EAGAIN);
 
 	if (!rc) {
+		/* All present CPUs must be online */
+		cpumask_andnot(offline_mask, cpu_present_mask,
+				cpu_online_mask);
+		rc = rtas_online_cpus_mask(offline_mask);
+		if (rc) {
+			pr_err("%s: Could not bring present CPUs online.\n",
+					__func__);
+			goto out;
+		}
+
 		stop_topology_update();
 		rc = pm_suspend(PM_SUSPEND_MEM);
 		start_topology_update();
+
+		/* Take down CPUs not online prior to suspend */
+		if (!rtas_offline_cpus_mask(offline_mask))
+			pr_warn("%s: Could not restore CPUs to offline "
+					"state.\n", __func__);
 	}
 
 	stream_id = 0;
 
 	if (!rc)
 		rc = count;
+out:
+	free_cpumask_var(offline_mask);
 	return rc;
 }
 
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index 97fe82ee863..2d3b1dd9571 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -361,7 +361,7 @@ static int wsp_chip_set_affinity(struct irq_data *d,
 	xive = xive_set_server(xive, get_irq_server(ics, hw_irq));
 	wsp_ics_set_xive(ics, hw_irq, xive);
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip wsp_irq_chip = {